{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4035522937774658, "min": 1.4035522937774658, "max": 1.425020456314087, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70771.3203125, "min": 69012.1875, "max": 78253.0703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.92833876221498, "min": 74.8517397881997, "max": 374.6865671641791, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49690.0, "min": 48677.0, "max": 50209.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999621.0, "min": 49956.0, "max": 1999621.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999621.0, "min": 49956.0, "max": 1999621.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5277814865112305, "min": 0.16648855805397034, "max": 2.5277814865112305, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1552.057861328125, "min": 22.14297866821289, "max": 1587.118408203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.941112610435641, "min": 1.7956196036105765, "max": 4.056448992608364, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2419.8431428074837, "min": 238.81740728020668, "max": 2498.6734765172005, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.941112610435641, "min": 1.7956196036105765, "max": 4.056448992608364, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2419.8431428074837, "min": 238.81740728020668, "max": 2498.6734765172005, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01582331078777012, "min": 0.013692194301014145, "max": 0.020470596886298154, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04746993236331036, "min": 0.02738438860202829, "max": 0.056084714766863414, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05566780819661088, "min": 0.022244593314826488, "max": 0.06365232194463412, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16700342458983264, "min": 0.044489186629652976, "max": 0.17712348339458306, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.628948790383328e-06, "min": 3.628948790383328e-06, "max": 0.000295338826553725, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0886846371149984e-05, "min": 1.0886846371149984e-05, "max": 0.0008443032185656, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120961666666667, "min": 0.10120961666666667, "max": 0.19844627500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30362885, "min": 0.20755479999999998, "max": 0.5814344000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.035987166666658e-05, "min": 7.035987166666658e-05, "max": 0.0049224691224999985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021107961499999974, "min": 0.00021107961499999974, "max": 0.014073576559999999, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709046535", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709048923" }, "total": 2388.418324151, "count": 1, "self": 0.44340654099960375, "children": { "run_training.setup": { "total": 0.05060708199994224, "count": 1, "self": 0.05060708199994224 }, "TrainerController.start_learning": { "total": 2387.924310528, "count": 1, "self": 4.434106867097853, "children": { "TrainerController._reset_env": { "total": 3.3953948339999442, "count": 1, "self": 3.3953948339999442 }, "TrainerController.advance": { "total": 2379.9815212499025, "count": 233170, "self": 4.626199215951601, "children": { "env_step": { "total": 1873.94257725294, "count": 233170, "self": 1554.449798266057, "children": { "SubprocessEnvManager._take_step": { "total": 316.75016622099247, "count": 233170, "self": 16.43504235798582, "children": { "TorchPolicy.evaluate": { "total": 300.31512386300665, "count": 222995, "self": 300.31512386300665 } } }, "workers": { "total": 2.742612765890499, "count": 233170, "self": 0.0, "children": { "worker_root": { "total": 2380.7976161599972, "count": 233170, "is_parallel": true, "self": 1108.401533623964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009715579999465263, "count": 1, "is_parallel": true, "self": 0.0002706349998788937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007009230000676325, "count": 2, "is_parallel": true, "self": 0.0007009230000676325 } } }, "UnityEnvironment.step": { "total": 0.049284536999948614, "count": 1, "is_parallel": true, "self": 0.00038036499995541817, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019819099998130696, "count": 1, "is_parallel": true, "self": 0.00019819099998130696 }, "communicator.exchange": { "total": 0.04798618700010593, "count": 1, "is_parallel": true, "self": 0.04798618700010593 }, "steps_from_proto": { "total": 0.0007197939999059599, "count": 1, "is_parallel": true, "self": 0.0002026509998813708, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005171430000245891, "count": 2, "is_parallel": true, "self": 0.0005171430000245891 } } } } } } }, "UnityEnvironment.step": { "total": 1272.3960825360332, "count": 233169, "is_parallel": true, "self": 40.908131902891455, "children": { "UnityEnvironment._generate_step_input": { "total": 82.28314852497624, "count": 233169, "is_parallel": true, "self": 82.28314852497624 }, "communicator.exchange": { "total": 1057.7090457500112, "count": 233169, "is_parallel": true, "self": 1057.7090457500112 }, "steps_from_proto": { "total": 91.49575635815427, "count": 233169, "is_parallel": true, "self": 32.33019355914007, "children": { "_process_rank_one_or_two_observation": { "total": 59.1655627990142, "count": 466338, "is_parallel": true, "self": 59.1655627990142 } } } } } } } } } } }, "trainer_advance": { "total": 501.4127447810106, "count": 233170, "self": 6.5196801820313794, "children": { "process_trajectory": { "total": 152.33397764297683, "count": 233170, "self": 151.00120010397654, "children": { "RLTrainer._checkpoint": { "total": 1.3327775390002898, "count": 10, "self": 1.3327775390002898 } } }, "_update_policy": { "total": 342.5590869560024, "count": 97, "self": 277.5838471069894, "children": { "TorchPPOOptimizer.update": { "total": 64.97523984901295, "count": 2910, "self": 64.97523984901295 } } } } } } }, "trainer_threads": { "total": 9.099999260797631e-07, "count": 1, "self": 9.099999260797631e-07 }, "TrainerController._save_models": { "total": 0.11328666700001122, "count": 1, "self": 0.001976259000002756, "children": { "RLTrainer._checkpoint": { "total": 0.11131040800000847, "count": 1, "self": 0.11131040800000847 } } } } } } }